GoogLeNet是由谷歌的Szegedy, Christian等人在《Going Deeper With Convolutions【CVPR-2015】》【论文地址】一文中提出的模型,主要特点是提高了网络内部计算资源的利用率,允许增加网络的深度和宽度,同时保持计算预算不变。
此前传统的方式简单粗暴的增加隐藏层(网络深度)和各层神经元数目(网络宽度)以达到提高网络性能的目的, 但这类方法存在致命的问题:更大的参数空间需要更多的计算资源并且更容易导致过拟合;网络越深则梯度越容易消失导致优化更加困难。
卷积神经网络的性能提高都是依赖于提高网络的深度和宽度,如何在增加网络深度和宽度的同时减少参数?解决思路便是全连接变成稀疏连接,GoogLeNet从网络结构上入手,改变了网络结构,提出了inception的卷积网络结构:
原始的(基本)Inception模块,其通过多个尺寸上进行卷积再聚合,来提取更密集的特征。
对输入做了4个分支,分别用不同尺寸的filter进行卷积或池化,最后再在特征维度上拼接到一起,以便下一阶段能够同时从不同的尺度上提取特征。这种全新的结构设计能带来以下好处:
原始的Inception 结构存在一个不可忽视的问题:卷积运算运算量过大,如果特征图的通道数过大(即当上一层的输出通道数较大时)会导致当前Inception模块的运算消费巨大,特别是当前Inception模块中的pooling层输出的通道数和输入保持一致,且由于多组卷积核并联运算,因此这是随着层数的堆叠而爆炸式增长的!
针对这一问题对原始结构做了改进,加上1x1卷积层作为reduction层做降维和特征映射、空间信息整合和引入非线性,以达到网络的压缩从而减少计算量。
1x1卷积在卷积神经网络中起着重要的作用:
参数量:
使用128个3x3的卷积核对512通道特征图进行卷积:512×3×3×128=589824
使用24个1x1卷积核先对512通道特征图降维,再用128个3x3的卷积核进行卷积:512×1×1×24+24×3×3×128=12504
1x1卷积成为设计高效、灵活和强大的网络架构的重要工具。
在GoogLeNet中,除了主要的分类器外,还在网络的中间层添加了两个辅助分类器,提供了额外的监督信号,帮助网络更好地学习特征表示。
辅助分类器的作用和优势:
需要注意的是,辅助分类器并不直接用于最终的预测结果。在训练过程中,辅助分类器的损失函数会被加权,并与主分类器的损失函数相结合。在推理阶段,辅助分类器被舍弃,仅使用主分类器进行预测。
辅助分类器的添加是GoogLeNet架构的一个重要设计特点,也为后续的深度卷积神经网络的发展奠定了基础。
下图是原论文给出的关于VGGnet模型结构的详细示意图:
GoogLeNet在图像分类中分为两部分:backbone部分: *主要由InceptionV1模块、卷积层和池化层(汇聚层)组成,分类器部分: 由主分类器和俩个辅助分类器组成。
卷积层组: 卷积层+激活函数
# 卷积组:Conv2d+ReLU
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.relu(x)
return x
InceptionV1模块: 卷积层组+池化层
# InceptionV1:BasicConv2d+MaxPool2d
class InceptionV1(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(Inception, self).__init__()
# 1×1卷积
self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
# 1×1卷积+3×3卷积
self.branch2 = nn.Sequential(
BasicConv2d(in_channels, ch3x3red, kernel_size=1),
BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1) # 保证输出大小等于输入大小
)
# 1×1卷积+5×5卷积
self.branch3 = nn.Sequential(
BasicConv2d(in_channels, ch5x5red, kernel_size=1),
BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保证输出大小等于输入大小
)
# 3×3池化+1×1卷积
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
BasicConv2d(in_channels, pool_proj, kernel_size=1)
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
# 拼接
outputs = [branch1, branch2, branch3, branch4]
return torch.cat(outputs, 1)
辅助分类器: 池化层+卷积层组+全连接层+dropout
# 辅助分类器:AvgPool2d+BasicConv2d+Linear+dropout
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
# 池化层
self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
# 1×1卷积
self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]
# 全连接层
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, num_classes)
def forward(self, x):
# aux1: N x 512 x 14 x 14
# aux2: N x 528 x 14 x 14
x = self.averagePool(x)
# aux1: N x 512 x 4 x 4
# aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = torch.flatten(x, 1)
x = F.dropout(x, 0.5, training=self.training)
# N x 2048
x = F.relu(self.fc1(x), inplace=True)
x = F.dropout(x, 0.5, training=self.training)
# N x 1024
x = self.fc2(x)
# N x num_classes
return x
import torch.nn as nn
import torch
import torch.nn.functional as F
from torchsummary import summary
class GoogLeNet(nn.Module):
def __init__(self, num_classes=1000, aux_logits=True, init_weights=False):
super(GoogLeNet, self).__init__()
self.aux_logits = aux_logits
self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.conv2 = BasicConv2d(64, 64, kernel_size=1)
self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception3a = InceptionV1(192, 64, 96, 128, 16, 32, 32)
self.inception3b = InceptionV1(256, 128, 128, 192, 32, 96, 64)
self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception4a = InceptionV1(480, 192, 96, 208, 16, 48, 64)
self.inception4b = InceptionV1(512, 160, 112, 224, 24, 64, 64)
self.inception4c = InceptionV1(512, 128, 128, 256, 24, 64, 64)
self.inception4d = InceptionV1(512, 112, 144, 288, 32, 64, 64)
self.inception4e = InceptionV1(528, 256, 160, 320, 32, 128, 128)
self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)
self.inception5a = InceptionV1(832, 256, 160, 320, 32, 128, 128)
self.inception5b = InceptionV1(832, 384, 192, 384, 48, 128, 128)
if self.aux_logits:
self.aux1 = InceptionAux(512, num_classes)
self.aux2 = InceptionAux(528, num_classes)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.dropout = nn.Dropout(0.4)
self.fc = nn.Linear(1024, num_classes)
if init_weights:
self._initialize_weights()
def forward(self, x):
# N x 3 x 224 x 224
x = self.conv1(x)
# N x 64 x 112 x 112
x = self.maxpool1(x)
# N x 64 x 56 x 56
x = self.conv2(x)
# N x 64 x 56 x 56
x = self.conv3(x)
# N x 192 x 56 x 56
x = self.maxpool2(x)
# N x 192 x 28 x 28
x = self.inception3a(x)
# N x 256 x 28 x 28
x = self.inception3b(x)
# N x 480 x 28 x 28
x = self.maxpool3(x)
# N x 480 x 14 x 14
x = self.inception4a(x)
# N x 512 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux1 = self.aux1(x)
x = self.inception4b(x)
# N x 512 x 14 x 14
x = self.inception4c(x)
# N x 512 x 14 x 14
x = self.inception4d(x)
# N x 528 x 14 x 14
if self.training and self.aux_logits: # eval model lose this layer
aux2 = self.aux2(x)
x = self.inception4e(x)
# N x 832 x 14 x 14
x = self.maxpool4(x)
# N x 832 x 7 x 7
x = self.inception5a(x)
# N x 832 x 7 x 7
x = self.inception5b(x)
# N x 1024 x 7 x 7
x = self.avgpool(x)
# N x 1024 x 1 x 1
x = torch.flatten(x, 1)
# N x 1024
x = self.dropout(x)
x = self.fc(x)
# N x 1000(num_classes)
if self.training and self.aux_logits: # 训练阶段使用
return x, aux2, aux1
return x
# 对模型的权重进行初始化操作
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
if m.bias is not None:
nn.init.constant_(m.bias, 0)
elif isinstance(m, nn.Linear):
nn.init.normal_(m.weight, 0, 0.01)
nn.init.constant_(m.bias, 0)
# InceptionV1:BasicConv2d+MaxPool2d
class InceptionV1(nn.Module):
def __init__(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj):
super(InceptionV1, self).__init__()
# 1×1卷积
self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)
# 1×1卷积+3×3卷积
self.branch2 = nn.Sequential(
BasicConv2d(in_channels, ch3x3red, kernel_size=1),
BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1) # 保证输出大小等于输入大小
)
# 1×1卷积+5×5卷积
self.branch3 = nn.Sequential(
BasicConv2d(in_channels, ch5x5red, kernel_size=1),
# 在官方的实现中,其实是3x3的kernel并不是5x5,这里我也懒得改了,具体可以参考下面的issue
# Please see https://github.com/pytorch/vision/issues/906 for details.
BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2) # 保证输出大小等于输入大小
)
# 3×3池化+1×1卷积
self.branch4 = nn.Sequential(
nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
BasicConv2d(in_channels, pool_proj, kernel_size=1)
)
def forward(self, x):
branch1 = self.branch1(x)
branch2 = self.branch2(x)
branch3 = self.branch3(x)
branch4 = self.branch4(x)
# 拼接
outputs = [branch1, branch2, branch3, branch4]
return torch.cat(outputs, 1)
# 辅助分类器:AvgPool2d+BasicConv2d+Linear+dropout
class InceptionAux(nn.Module):
def __init__(self, in_channels, num_classes):
super(InceptionAux, self).__init__()
# 池化层
self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3)
# 1×1卷积
self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]
# 全连接层
self.fc1 = nn.Linear(2048, 1024)
self.fc2 = nn.Linear(1024, num_classes)
def forward(self, x):
# aux1: N x 512 x 14 x 14
# aux2: N x 528 x 14 x 14
x = self.averagePool(x)
# aux1: N x 512 x 4 x 4
# aux2: N x 528 x 4 x 4
x = self.conv(x)
# N x 128 x 4 x 4
x = torch.flatten(x, 1)
x = F.dropout(x, 0.5, training=self.training)
# N x 2048
x = F.relu(self.fc1(x), inplace=True)
x = F.dropout(x, 0.5, training=self.training)
# N x 1024
x = self.fc2(x)
# N x num_classes
return x
# 卷积组: Conv2d+ReLU
class BasicConv2d(nn.Module):
def __init__(self, in_channels, out_channels, kernel_size, stride=1, padding=0):
super(BasicConv2d, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
x = self.conv(x)
x = self.relu(x)
return x
if __name__ == '__main__':
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = GoogLeNet().to(device)
summary(model, input_size=(3, 224, 224))
summary可以打印网络结构和参数,方便查看搭建好的网络结构。
尽可能简单、详细的介绍了深度可分卷积的原理和卷积过程,讲解了GoogLeNet(InceptionV1)模型的结构和pytorch代码。